• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Predicting Motion of Engine-Ingested Particles Using Deep Neural Networks

Bowman, Travis Lynn 01 August 2022 (has links)
The ultimate goal of this work is to facilitate the design of gas turbine engine particle separators by reducing the computational expense to accurately simulate the fluid flow and particle motion inside the separator. It has been well-documented that particle ingestion yields many detrimental impacts for gas turbine engines. The consequences of ice particle ingestion can range from surface-wear abrasion to engine power loss. It is known that sufficiently small particles, characterized by small particle response times (τp), closely follow the fluid trajectory whereas large particles deviate from the streamlines. Rather than manually deriving how the particle acceleration varies from the fluid acceleration, this work chooses to implicitly derive this relationship using machine learning (ML). Inertial particle separators are devices designed to remove particles from the engine intake flow, which contributes to both elongating the lifespan and promoting safer operation of aviation gas turbine engines. Complex flows, such as flow through a particle separator, naturally have rotation and strain present throughout the flow field. This study attempts to understand if the motion of particles within rotational and strained canonical flows can be accurately predicted using supervised ML. This report suggests that preprocessing the ML training data to the fluid streamline coordinates can improve model training. ML models were developed for predicting particle acceleration in laminar, fully rotational/irrotational flows and combined laminar flows with rotation and strain. Lastly, the ML model is applied to particle data extracted from a Computational Fluid Dynamics (CFD) study of particle-laden flow around a louver-geometry. However, the model trained with particle data from combined canonical flows fails to accurately predict particle accelerations in the CFD flow field. / Master of Science / Aviation gas turbine engine particle ingestion is known to reduce engine lifespans and even pose a threat to safe operation in the worst case. Particles being ingested into an engine can be modeled using multiphase flow techniques. Devices called inertial particle separators are designed to remove particles from the flow into the engine. One challenge with designing such a separator is figuring out how to efficiently expel the small particles from the flow while not unnecessarily increasing pressure loss with excessive twists and turns in the geometry. Designers usually have to develop such geometries using multiphase flow computational fluid dynamics (CFD) that solve the fluid and particle dynamics. The abundance of data associated with CFD, and especially multiphase flows make it an ideal application to study with machine learning (ML). Because such multiphase simulations are very computationally expensive, it is desirable to develop "cheaper" methods. This is the long term goal of this work; we want to create ML surrogates that decrease the computational cost of simulating the particle and fluid flow in particle separator geometries such that designs can be iterated more quickly. In this work we introduce how artificial neural networks (ANNs), which are a tool used in ML, can be used to predict particle acceleration in fluid flow. The ANNs are shown to learn the acceleration predictions with acceptable accuracy for the training data generated with canonical flow cases. However, the ML model struggles to become generalizable to actual CFD simulations.
2

Rotorcraft engine air particle separation

Bojdo, Nicholas Michael January 2012 (has links)
The present work draws together all current literature on particle separating devices and presents a review of the current research on rotor downwash-induced dust clouds. There are three types of particle separating device: vortex tube separators; inlet barrier filters; and inlet particle separators. Of the three, the latter has the longest development history; the former two are relatively new retrofit technologies. Consequently, the latter is well-represented in the literature, especially by computational fluid dynamics simulations, whereas the other two technologies, with specific application to rotorcraft, are found to be lacking in theoretical or numerical analyses. Due to their growing attendance on many rotorcraft currently in operation, they are selected for deeper investigation in the present work.The inlet barrier filter comprises a pleated filter element through which engine bound air flows, permitting the capture of particles. The filter is pleated to increase its surface area, which reduces the pressure loss and increases the mass retention capability. As particles are captured, the filter's particle removal rate increases at the expense of pressure loss. The act of pleating introduces a secondary source of pressure loss, which gives rise to an optimum pleat shape for minimum pressure drop. Another optimum shape exists for maximum mass retention. The two optimum points however are not aligned. In the design of inlet barrier filters both factors are important. The present work proposes a new method for designing and analysing barrier filters. It is found that increasing the filter area by 20% increases cycle life by 46%. The inherent inertial separation ability of side-facing intakes decreases as particles become finer; for the same fine sand, forward-facing intakes ingest 30% less particulate than side-facing intakes. Knowledge of ingestion rates affords the prediction of filter endurance. A filter for one helicopter is predicted to last 8.5 minutes in a cloud of 0.5 grams of dust per cubic metre, before the pressure loss reaches 3000 Pascals. This equates to 22 dust landings.An analytical model is adapted to determine the performance of vortex tube separators for rotorcraft engine protection. Vortex tubes spin particles to the periphery by a helical vane, whose pitch is found to be the main agent of efficacy. In order to remove particles a scavenge flow must be enacted, which draws a percentage of the inlet flow. This is also common to the inlet particle separator. Results generated from vortex tube theory, and data taken from literature on inlet particle separators permit a comparison of the three devices. The vortex tube separators are found to achieve the lowest pressure drop, while the barrier filters exhibit the highest particle removal rate. The inlet particle separator creates the lowest drag. The barrier filter and vortex tube separators are much superior to the inlet particle separator in improving the engine lifetime, based on erosion by uncaptured particles. The erosion rate predicted when vortex tube separators are used is two times that of a barrier filter, however the latter experiences a temporal (but recoverable post-cleaning) loss of approximately 1% power.

Page generated in 0.1161 seconds